Model comparison
GPT-4 Turbo vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 30.5 on the Noometry Index.
Last verified . 31 shared benchmarks.
Mistral AISummary
- They share 31 benchmarks with published results for both. GPT-4 Turbo scores higher in 2 categories and Mistral Large in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large leads 18.2 to 9.0.
- The biggest single-benchmark swing is BigCodeBench Complete: 58.2% for GPT-4 Turbo and 38.3% for Mistral Large.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Mistral Large accepts more context: 131K tokens versus 128K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 30.5 | 31.9 |
| Released | 2023-11-06 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 4K | 16K |
| Input $ / M tokens | $10 | $2 |
| Output $ / M tokens | $30 | $6 |
| Results tracked | 36 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4 Turbo: 33.8 (#249), Mistral Large: 34.3 (#240)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 30% |
| LMArena Coding | 1268 | 1277 |
| BigCodeBench Complete | 58.2% | 38.3% |
| HumanEval+ | 86.6% | 62.2% |
| MBPP+ | 73.3% | 59.5% |
| SciCode | — | 36.2% |
| WeirdML | 18% | — |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | — | 264.7 |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Mistral Large: 28.6 (#89)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| METR Time Horizons | 36.7% | — |
Reasoning Too close to call
GPT-4 Turbo: 15.3 (#317), Mistral Large: 15.8 (#310)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| SimpleBench | 25.1% | 22.5% |
| LMArena Hard Prompts | 1251 | 1257 |
| DTBench | 61.6% | 65.1% |
| LMCA | 9.8% | 16.7% |
| Epoch Capabilities Index | 127.25 | 128.52 |
| ForecastBench | 59.4 | 57.1 |
| CritPt | — | 0% |
| Chess Puzzles | 6% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |
Math Mistral Large leads
GPT-4 Turbo: 9.0 (#322), Mistral Large: 18.2 (#291)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 8.5% |
| LMArena Math | 1272 | 1262 |
| MATH Level 5 | 46.7% | 50.3% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mistral Large leads
GPT-4 Turbo: 24.3 (#268), Mistral Large: 30.1 (#230)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| GPQA Diamond | 46.6% | 51.3% |
| Confabulations | 28.4% | 21.4% |
| LMArena Expert | 1223 | 1232 |
| MMLU | 81.3% | 80% |
| MMLU-Pro | — | 59.9% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), Mistral Large: —
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Too close to call
GPT-4 Turbo: 40.5 (#216), Mistral Large: 40.0 (#219)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| LMArena Non-English | 1245 | 1237 |
| LMArena Chinese | 1242 | 1240 |
| LMArena French | 1276 | 1325 |
| LMArena German | 1259 | 1254 |
| LMArena Japanese | 1194 | 1188 |
| LMArena Korean | 1187 | 1202 |
| LMArena Russian | 1259 | 1257 |
| LMArena Spanish | 1260 | 1268 |
Instruction Following Mistral Large leads
GPT-4 Turbo: 65.8 (#216), Mistral Large: 67.9 (#191)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1249 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Too close to call
GPT-4 Turbo: 38.0 (#206), Mistral Large: 38.3 (#199)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1254 | 1261 |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.7 (#206), Mistral Large: 40.7 (#242)
| Benchmark | GPT-4 Turbo | Mistral Large |
|---|---|---|
| LMArena Text | 1272 | 1266 |
| LMArena Creative Writing | 1269 | 1243 |
| LMArena Multi-Turn | 1267 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GPT-4 Turbo better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 30.5 on the Noometry Index.
Which is cheaper, GPT-4 Turbo or Mistral Large?
Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Mistral Large better for coding?
They score almost the same on coding (33.8 vs 34.3); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 128K.
How many benchmarks do GPT-4 Turbo and Mistral Large share?
31 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Mistral Large has 51.